Algorithms for PAC Learning of Functions with Smoothness Properties
|
|
- April Simpson
- 5 years ago
- Views:
Transcription
1 Algorithms for PAC Learning of Functions with Smoothness Properties Nageswara S. V. Rao and Vladimir A. Protopopescu Center for Engineering Systems Advanced Research P. 0. Box 2008 Oak Ridge National Laboratory Oak Ridge, Tennessee { raons,pro t op op gov The submitted manuscript haa been authored by a contractor of the U.S. Government under contr.ct No. DE AC05-(llOR Accordingly, the US. Government retains a nonexclurive, royalty-free license to puhlirh or reproduce the published form of this contribution, or allow othcrr to do so, for US. Government purpoaes. Paper submitted to Fourth International Symposium on Artificial Intelligence and Mathematics, January 3-5, 1996, Fort Lauderdale, Florida. tresearch sponsored by the Engineering Research Program of the Office of Basic Energy Sciences, of the U.S. Department of Energy, under Contract No. DE-AC05-840R21400 with Martin Marietta Energy Systems, Inc. 1
2 Algorithms for PAC Learning of Functions with Smoothness Properties Nageswara S. V. Rao and Vladimir A. Protopopescu Center for Engineering Systems Advanced Research Oak Ridge National Laboratory Oak Ridge, Tennessee {raons, Summary - We present three computationally efficient algorithms for Probably and Approtimately Correct (PAC) learning of an unknown function f : [0, lid t-+ [0,1], based on finite samples. The function f is chosen from the family 3 n C([O, lid) or T n C"([O, l]'), where F has either bounded modulus of smoothness or bounded capacity or both. Three function estimators based on: (i) local averaging, (ii) nearest neighbor rule, and (iii) Nadaraya-Watson estimator, all computed using the Haar system, are analyzed. With no preprocessing of the sample, estimated function value at a given point can be computed in O ( n )time. With preprocessing, the first and third estimators can be computed in O((1og T Z ) ~time ) using a range-tree precomputed in O(dn(1og n ) d )time. Introduction The problem of learning functions in the PAC learning framework of (Valiant 1984) continues to generate significant interest and activity (Alon et al. 1993; Bartlett, Long, & Williamson 1994; Ben-David et al. 1992; Kimber & Long 1992; Apsitis, Freivalds, & Smith 1995). Initial efforts have been concentrated on indicator functions and functions on simpler domains (Natarajan 1991) with increasing attention being paid to real functions (Auer et al. 1993; Simon 1994). Recent results establish that a function that achieves small empirical error on an independently and identically distributed sample yields a PAC a p proximation, under the finiteness of a combinatorial parameter such as the fat-shattering index (Bartlett, Long, & Williamson 1994; Anthony & Bartlett 1994). The difficulties of computing such PAC estimators for functions are well-known in that the problem is NPcomplete even for simple indicator function classes (Blumer e i al. 1989; Pitt & Valiant 1988). We show that mild smoothness properties enable us to identify such classes and to actually construct computationally eficient function estimators that guarantee PAC type results. Our algorithms are applicable to more general cases than in (Kimber & Long 1992) and also yieid lower computational complexity than those in (Auer et af. 1993). Regression estimation problem, which subsumes the function estimation problem, is well-known in the statistics literature (Rao 1983; Brieman et al. 1984). Typical statistical consistency results of regression estimates are asymptotic and do not yield finite sample results required by the PAC paradigm with the exception of some results that utilize Borel-Cantelli Lemma (Nadaraya 1970). On the other hand, a key attractive feature of some of these methods is their low computationally complexity. In general, complexity measures such as the finite capacity (Vapnik 1982) or the fat-shattering index (Anthony & Bartlett 1994; Bartlett, Long, & Williamson 1994) and the smoothness properties of functions do not imply each other. We show that the two types of conditions can be combined to yield low complexity under mild additional restrictions that preserve the strength of PAC method without over-constraining the problem. We study three function estimators based on: (i) local averaging, (ii) nearest neighbor rule, and (iii) Nadaraya-Watson estimator, all computed using the Haar system. For these estimators, we provide PAC results on function error based on a randomly chosen point, expected error, and supremum of the error, respectively. The estimated function value at a given point can be computed in O(n) time, for all three cases, and with preprocessing, the first and third can be computed in O((logn)d) time using a range-tree precomputed in O(dn(1og n ) d )time. Our results differ from those based on capacity (or related combinatorial parameters) in two directions: (a) under mild smoothness conditions on the function and/or the density, we can obtain stronger guarantees for the error between the function and the estimator; and, (b) our estimators can be computed in linear time, unlike the general PAC solutions that usually require solving NP-hard problems. A brief comparison with feedforward sigmoidal neural networks indicates that our nearest neighbor estimate approximates a neural network based estimator within the PAC paradigm. The proofs of the theorems presented in this paper will appear elsewhere (Rao & Protopopescu 1995).
3 Preliminaries Let Q = [O,lId, and let C(Q) and P ( Q ) denote the classes of continuous and essentially bounded functions defined on Q,respectively. For f E L"O(Q),we have II f llm= as e s s s ~ ~ { l f ( z :) 2 l E &I. The modulus of smoothness off E L"O(Q)is defined Then an estimator for a density p E C"O(Q) based on n-sample is given by (Ciesielski 1988) which can also be written in the form fim.n(z)= n ( J ) h j ( z ) with n(j) = il{j : Xj E J)I and J Qm u w ( f r; ) = SUP Ihloo<r (ess SUP Q(h) If(%+ h) - f(z)i) + where Q ( h ) = {z E Q : z h E Q } and lhla = max(lh11,..., / / a d ( ). We note that for continuous functions, f E C(Q), the modulus of smoothness coincides with the ordinary modulus of continuity defined as The following identity is established in (Vapnik 1982): ifnsk H { A, } ( n ) = 2" < 1. 5 g if n > A. H5re A: is called the Vapnik-Chervonenkzs (VC) dimension of the family of sets A,. For a set of functions, the capacity (Vapnik 1989) is defined as the largest number h of pairs (zi,yj) that can be subdivided in all possible ways into two classes by means of rules of the form {O[(y- f(z))' ] ) ( j, p ) where f E 3,j? E W, and Q ( z ) is the Heaviside stepfunction defined as { e(%) = 1 ifz>o 0 fz<0. Thus the capacity of a family of functions 3 is the VC dimension of the set of indicator functions {Q[(y- fw2+ P l 1 ( f, P ) E F X S 1. For rn = 0, 1,..., let Q, denote a famiiy of diadic cubes such that [0, lid= U J, JnJ' = 0 for J # J', JEQm and the d-dimensional volume of J, denoted by IJI, is 2-dm. Let l~(z)denote the indicator function of J E Qm: lj(t) = 1 if z E J, and ~ J ( z=) 0 otherwise. For given rn, we define P, : Coo(&) Cm(Q) by c.$ for z E J and J E Q, (Ciesielski 1988). Consider a kernel given by P,(z, y) = 2dm 1J ( z )~~( y )for JEQm &YEQ. h ~ ( z=) mlj(z)lemma 1 (Ciesielski 1988) Let 0 < a 5 1 and f E C ( Q ) or f E P ( Q ) be given. Then the condition w ( f;r ) = O(ra) as r --+ O+ implies 11 f - P, f Iloo= as rn O(1/2am) PAC Estimators for Continuous Functions We consider three types of function estimators. The first is a local estimator based on "averaging" the function values within each cell of suitably chosen Qm. The second one is based on the nearest neighbor rule applied to each cell of &., When the functions have bounded moduli of smoothness, these estimators provide distribution-free results. The third estimator, called Nadaraya-Watson, applies to a more particular case where the density exists and also satisfies some smoothness properties. Not surprisingly, the Nadaraya-Watson estimator based on the Haar system provides better guarantees. Local Averaging Based on the n-sample, the first estimator of the function f is given by. which evaluates to n C XjEJ w, for z E J. Estimators of this general structure are called regressograms (Rao 1983) (this estimator, however, is not identical to the traditional regressogram). The next theorem provides a finite sample result for this estimate. Theorem 1 Consider a family of continuous functions 3 C C([O, lid), with range [0,1] and capacity h such that for every f E F,we have um(f;r ) = O(r") as r 0, f o r 0 < a 5 1. Suppose that the size of the sample, n, is larger than --+ 'Some additional measurability conditions are required F,which are assumed to be satisfied throughout the paper (Pollard 1984). on
4 where m = $log(4c/r6) is larger than a suitable constant mo. Then for any X chosen according to the distribution Px and any f E 3, we have P [ M X ) - fm,n(x)i > 1 < 6. Local Nearest Neighbor Rule Based on the n-sample, the second estimator for the function f is given by fm,n(x) = 1J(x)n/J(Z) JEBm where for 2 E J, N j ( x ) yields f ( X i ) such that Xi E J is closest to x in sup norm. As shown later, this estimator has a higher computational complexity than the other two when preprocessing is not allowed and also provides a weaker performance guarantee. The trade-off is that it only requires a bounded modulus of smoothness and does not require bounded capacity. Theorem 2 Consider a family of continuous functions F C C([O, lid), with range [0,1] such that for, every f E F, we have woo(f;r) = O(ro) as r -+ 0, for 0 < CY 5 1. Suppose that the size of the sample, n, is larger than kzd3e22m+2 k2d3e23m+2 In2 2 &2 +2 ( ) where k = C/2um and m = Llog(4C/c6) is larger than a suitable mo. For X distri&uted according to Px and any f E 3, we have P [Elf ( X ) - fm,n(x)i > < 6. 1 Nadaraya-Watson Estimator We now present the third estimator that provides a better guarantee under additional conditions on the densities (simiiar in some sense to (Sakai, Takimoto, & Maruoka 1995)). Based on the n-sample, the estimator is defined by n where 0 < p < d/2(a + d), rn = r-1 f E T, we have P If(2) - fm,n(z)i> and X = c Computing the Estimates Computation of estimators fm,n(z) or fm,n (z) at given t involves obtaining the local sum of f ( X i ) ' s that are contained in J containing x. The range-tree (Preparata & Shamos 1985) can be constructed to store the cells J that contain at least one Xi; with each such cell we store the number of the Xi's that are contained in J and the s u m of the corresponding f(xi)'s. This computation can be achieved by known methods (Preparata & Shamos 1985), and the values corresponding to J that contains z can be retrieved or f,,,n(x) can in O((logn)d) time, and then fm,n(z) be computed in additional constant time. This same structure can be used to store the training sample o_f each J; once J containing x has been identified, fm,n(z) can be computed in linear time. Theorem 4 The estimators fm,n(z),j,,+(z), and Z;n,n(+) at given x E [O,1jd can be computed in O(n) time. Based on a preprocessing in O(n(1o n d-l time, resulting in a structure of size O(n(1og n)pi-) ), the estt' motor im,n(x) or fm.,,(z)for given z can be computed in O((1og n ) d ) time. LOO-Functions Recall that C([O, lid) c t " ( [ O, lid) and the latter allows for discontinuities in the functions. Only minor changes to the proofs of results in last section are needed to establish analogous results for t w ( [ O, lid). Approximation to Neural Networks We consider a feedforward network with a single hidden layer of m hidden nodes and a single output node. The output of the j t h hidden node is a(b?z t j ), where x E [ O, l l d, bj E?Xd, t j E 8,bTx is the scalar product, and the monotonically increasing function u :?X w [O,11 is called an activation function. The output of the network corresponding to input x is + for z E J. Estimators of this general structure are called Nadaraya-Watson kernel estimators.(rae 1983). Here we use the kernels generated by the Haar functions (Engel 1994). Theorem 3 Consider a family of functions F C_ C([O, 1Id) with range [0,1]and capacity h < 00 such that wm(f;r) = O(rP) as r + 0, for 0 < CY 5 1. We assume that: (i) there ezists a family of densities P E C([O, ljd); (ii) for each p E P,w,(p; r) = O(ra) as r + 0, for 0 < Q 5 1; and (iii) there ezists p > 0 such that f o r each p E P,p(x) > p. Suppose that the sample size, n, is larger than m where a = ( a l,0 2,..., a m ) E?Xm and w is the weight vector of the network consisting of a, bl, b2,...,b, and t f, t 2,...,tm. We consider neural networks with bounded weights such that w E [-W,+W]"(d+l) for some fixed positive W < 00. We consider u ( z ) = 1/(1 e-y'), for 7, z E R. Let Fw = {fw : w E [-Wl+W]m(d+l)}. Then the nearest neighbor estimator fm,n can approximate any f E 3w to any desired accuracy in terms of the expected error. +
5 Corollary 1 For any f E F w,we have 4 p [ W X )- L, n ( W I > < 6 corresponding to the sample sire given in Theorem 2 with the Lipschitr constant k given by where u = mwlaji and b = miqxlbijl. a Tfi '$1 Note that boundedness of capacity of neural networks of this type can be deduced from the results of (Macintyre & Sontag 1993), which can be used t o obtain sample bounds along the lines of Theorem 1. The associated computation problem, however, is NPcomplete (Roychowdhury, Siu, & Orlitsky 1994). Thus it is of practical interest to approximate neural networks by the nearest neighbor rule that guarantees a PAC result is linear-time computable. Acknowledgements The authors acknowledge the guidance of Prof. Leo Brieman, Prof. Anselm Blumer and Dr.V. R. R. Uppuluri. This research is sponsored by the Engineering Research Program of the Office of Basic Energy Sciences, of the U.S. Department of Energy, under Contract No. DEAC05-840R21400 with Lockheed Martin Energy Systems, Inc. References Alon, N.; Ben-David, S.; Cesa-Bianchi, N.; and Hausler, D Scale-sensitive dimensions, uniform convergence, and learnability. In Proc. of 1993 IEEE Symp. on Foundations of Computer Science. Anthony, M., and Bartlett, P Function learning from interpolation. NeuroCOLT Technical Report Series NC-TR-94013, Royal Holloway, University of London. Apsitis, K.; F'reivalds, R.; and Smith, C. H On the inductive inference of real valued functions. In Proc. of 8th Ann. ACM Conf. on Computational Learning Theory. Auer, P.; Long, P. M.; Mass, W.; and Woeginger, G. J On the complexity of function learning. In Proc. of 6ih Ann. ACM Conf. on Computational Learning Theory, Bartlett, P. L.; Long, P. M.; and Williamson, R. C Fat-shattering and the learnability of realvalues fucntions. In Proc. of 7th Ann. ACM Conf. on Computational Learning Theory. Ben-David, S.; Cesa-Bianchi, N.; Haussler, D.; and Long, P Characterizations of learnability for classes (0,...,n)-valued functions. In Proc. of 5th Ann. ACM Conf. on Computational Learning Theory. Blumer, A.; Ehrenfeucht, A.; Haussler, D.; and Warmuth, M Learnability and the VapnikChervonenkis dimension. Journal of the Association of Computing Machinery 36(4): Brieman, L.; Friedman, J. H.; Olshen, R. A.; and Stone, C. J Classijcation and Regression Trees. Belmont, C A: Wadswor t h. Ciesielski, Z Haar system and nonparametric density estimation in several variables. Probability and Mathematical Statistics 9:l-11. Engel, J A simple wavelet approach to nonparametric regression from recursive partitioning schemes. Journal of Multivariate Analysis 49~ Kimber, D., and Long, P. M The learning complexity of smooth functions of a single variable. In Proc. of 1992 Workshop on Computational Learning, Macintyre, A., and Sontag, E. D Finiteness results for sigmoidal neural networks. In Proc. 25th Annual ACM Symp. on Theory of Computing Nadaraya, E. A Remarks on non-parametric estimates for density functions and regression curves. Theory of Probability and Applications 15: Natarajan, B. K Machine Learning: A Theoretical Approach. San Mateo, California: Morgan Kaufmann Pub. Inc. Pitt, L., and Valiant, L. G Computational limitations on learning from examples. Journal of the Association f o r Computing Machinery 35(4): Pollard, D Convergence of Stochastic Processes. New York: Springer-Verlag. Preparata, F. P., and Shamos, M. I Computational Geometry: An Introduction. Springer-Verlag. Rao, N. S. V., and Protopopescu, V. A Pac learning of functions with smoothness properties: Implications for feedforward sigmoidal networks. manuscript, to be published. Rao, B. L. S. P Nonparametric Functional Estimation. New York: Academic Press. Roychowdhury, V.; Siu, K.; and Orlitsky, A., eds Theoretical Advances in Neural Computation and Learning. Kluwer Academic Pub. Sakai, Y.; Takimoto, E.; and Maruoka, A Proper learning algorithm for functions of k terms under smooth distributions. In Proc. of 8th Ann. ACM Con$ on Computational Learning Theory. Simon, H. U Bounds on the number of examples needed for learning functions. In Shawe-Taylor, J., and Anthony, M., eds., Computational Learning Theory: EUROCOLT'93. Oxford University Press. Valiant, L. G A theory of the learnable. Communications of the ACM 27(11): Vapnik, V. N Estimation of Dependences Based on Empirical Data. New York: Springer Verlag. Vapnik, V. N Inductive principles of the search for empirical dependences. In Proceedings of Second Ann. Workshop on Computational Learning Theory, 3-21.
6 DISCLAIMER This report was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercia1 product, process, or service by trade name, trademark, manufac: turer, or otherwise does not necessarily constitute or imply its endorsement, m m- mendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.
Nearest Neighbor Rules PAC-Approximate Feedforward Networks t
Nearest Neighbor Rules PAC-Approximate Feedforward Networks t Nageswara S. V. Rao Center for Engineering Systems Advanced Research Oak Ridge National Laboratory Oak Ridge, Tennessee 37831-6364 email: raons@ornl.gov
More informationOn PAC Learning of Functions with Smoothness Properties Using Feedforward Sigmoidal Networks
On PAC Learning of Functions with Smoothness Properties Using Feedforward Sigmoidal Networks Nageswara S. V. Rao and Vladimir A. Protopopescu Center for Engineering Systems Advanced Research P. 0. Box
More informationA Result of Vapnik with Applications
A Result of Vapnik with Applications Martin Anthony Department of Statistical and Mathematical Sciences London School of Economics Houghton Street London WC2A 2AE, U.K. John Shawe-Taylor Department of
More informationExcitations of the transversely polarized spin density. waves in chromium. E3-r 1s
c Version: July 15, 1997 Excitations of the transversely polarized spin density waves in chromium W.-T. Lee a, S. A. Werner a, J. A. Fernandez-Baca b, and R. S. Fishman. a Department of Physics, University
More informationVapnik-Chervonenkis Dimension of Neural Nets
P. L. Bartlett and W. Maass: Vapnik-Chervonenkis Dimension of Neural Nets 1 Vapnik-Chervonenkis Dimension of Neural Nets Peter L. Bartlett BIOwulf Technologies and University of California at Berkeley
More informationDE '! N0V ?
"7 CONF-851174 24 DE86 004682 '! N0V26 1985? PREDICTION OF FLOW RATES THROUGH AN ORIFICE AT PRESSURES CORRESPONDING TO THE TRANSITION BETWEEN MOLECULAR AND ISENTROPIC FLOW S. F. DeMuth Fuel Recycle Division
More informationA note on the generalization performance of kernel classifiers with margin. Theodoros Evgeniou and Massimiliano Pontil
MASSACHUSETTS INSTITUTE OF TECHNOLOGY ARTIFICIAL INTELLIGENCE LABORATORY and CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES A.I. Memo No. 68 November 999 C.B.C.L
More informationData Comparisons Y-12 West Tower Data
Data Comparisons Y-12 West Tower Data Used hourly data from 2007 2010. To fully compare this data to the data from ASOS sites where wind sensor starting thresholds, rounding, and administrative limits
More informationUse of Gamma Rays from the Decay of 13.8-sec "Be to Calibrate a Germanium Gamma Ray Detector for Measurements up to 8 MeV
The submitted manuscript has been authored by a contractor of the U S Government under contract No W-31-109-ENG-38 Accordingly the U S Government retains a nonexclusive, royalty-free license to publish
More informationData-Dependent Structural Risk. Decision Trees. John Shawe-Taylor. Royal Holloway, University of London 1. Nello Cristianini. University of Bristol 2
Data-Dependent Structural Risk Minimisation for Perceptron Decision Trees John Shawe-Taylor Royal Holloway, University of London 1 Email: jst@dcs.rhbnc.ac.uk Nello Cristianini University of Bristol 2 Email:
More informationGA A26474 SYNERGY IN TWO-FREQUENCY FAST WAVE CYCLOTRON HARMONIC ABSORPTION IN DIII-D
GA A26474 SYNERGY IN TWO-FREQUENCY FAST WAVE CYCLOTRON HARMONIC ABSORPTION IN DIII-D by R.I. PINSKER, W.W. HEIDBRINK, M. PORKOLAB, F.W. BAITY, M. CHOI, J.C. HOSEA, and Y. ZHU JULY 2009 DISCLAIMER This
More informationOn Learnability, Complexity and Stability
On Learnability, Complexity and Stability Silvia Villa, Lorenzo Rosasco and Tomaso Poggio 1 Introduction A key question in statistical learning is which hypotheses (function) spaces are learnable. Roughly
More informationVapnik-Chervonenkis Dimension of Neural Nets
Vapnik-Chervonenkis Dimension of Neural Nets Peter L. Bartlett BIOwulf Technologies and University of California at Berkeley Department of Statistics 367 Evans Hall, CA 94720-3860, USA bartlett@stat.berkeley.edu
More informationSample width for multi-category classifiers
R u t c o r Research R e p o r t Sample width for multi-category classifiers Martin Anthony a Joel Ratsaby b RRR 29-2012, November 2012 RUTCOR Rutgers Center for Operations Research Rutgers University
More informationCQNl_" RESPONSE TO 100% INTERNAL QUANTUM EFFICIENCY SILICON PHOTODIODES TO LOW ENERGY ELECTRONS AND IONS
I ' 4 46 Title: CQNl_"- 461123-1.2 RESPONSE TO 100% INTERNAL QUANTUM EFFICIENCY SILICON PHOTODIODES TO LOW ENERGY ELECTRONS AND IONS A uthor(s): H. 0. Funsten D. M. Suszcynsky R. Korde S. M. Ritzau Submitted
More informationPROJECT PROGRESS REPORT (03/lfi?lfibr-~/15/1998):
F?ECEVVEI) N% 05 w PROJECT PROGRESS REPORT (03/lfi?lfibr-~/15/1998): A COMPREHENSIVE STUDY OF FRACTURE PATTERNS AND DENSITIES IN THE GEYSERS GEOTHERMAL RESERVOIR USING MICROEARTHQUAKE SHEAR-WAVE SPLITTING
More informationA Necessary Condition for Learning from Positive Examples
Machine Learning, 5, 101-113 (1990) 1990 Kluwer Academic Publishers. Manufactured in The Netherlands. A Necessary Condition for Learning from Positive Examples HAIM SHVAYTSER* (HAIM%SARNOFF@PRINCETON.EDU)
More informationRESEARCH OPPORTUNITIES AT THE CNS (Y-12 AND PANTEX) NUCLEAR DETECTION AND SENSOR TESTING CENTERS (NDSTC)
Y / DW-2319 RESEARCH OPPORTUNITIES AT THE CNS (Y-12 AND PANTEX) NUCLEAR DETECTION AND SENSOR TESTING CENTERS (NDSTC) Carter Hull 1 Carter.Hull@cns.doe.gov Jim Tallent 4, Dennis Tollefson 2, Martin Williamson
More informationRESONANCE INTERFERENCE AND ABSOLUTE CROSS SECTIONS IN NEAR-THRESHOLD ELECTRON-IMPACT EXCITATION OF MULTICHARGED IONS
RESONANCE INTERFERENCE AND ABSOLUTE CROSS SECTIONS IN NEAR-THRESHOLD ELECTRON-IMPACT EXCITATION OF MULTICHARGED IONS M. E. BANNISTER Physics Division, Oak Ridge National Labomtory, Oak Ridge, TN 37831-6372,USA
More information: Y/LB-16,056 OAK RIDGE Y-12 PLANT
Y-12 Report No.: Y/LB-16,056 OAK RIDGE Y-12 PLANT VERIFICATION OF URANIUM MASS AND ENRICHMENTS OF HIGHLY ENRICHED URANIUM (HEU) USING THE NUCLEAR MATERIALS IDENTIFICATION SYSTEM (NMIS) L. G. Chiang J.
More informationLQG/LTR ROBUST CONTROL SYSTEM DESIGN FOR A LOW-PRESSURE FEEDWATER HEATER TRAIN. G. V. Murphy J. M. Bailey The University of Tennessee, Knoxville"
LQG/LTR ROBUST CONTROL SYSTEM DESIGN FOR A LOW-PRESSURE FEEDWATER HEATER TRAIN G. V. Murphy J. M. Bailey The University of Tennessee, Knoxville" CONF-900464 3 DE90 006144 Abstract This paper uses the linear
More informationMulti-Scale Chemical Process Modeling with Bayesian Nonparametric Regression
Multi-Scale Chemical Process Modeling with Bayesian Nonparametric Regression Evan Ford, 1 Fernando V. Lima 2 and David S. Mebane 1 1 Mechanical and Aerospace Engineering 2 Chemical Engineering West Virginia
More informationOptimization of NSLS-II Blade X-ray Beam Position Monitors: from Photoemission type to Diamond Detector. P. Ilinski
BNL-94868-2013-CP Optimization of NSLS-II Blade X-ray Beam Position Monitors: from Photoemission type to Diamond Detector P. Ilinski Submitted to Journal of Physics: Conference Series March 2013 Photon
More informationRademacher Averages and Phase Transitions in Glivenko Cantelli Classes
IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 48, NO. 1, JANUARY 2002 251 Rademacher Averages Phase Transitions in Glivenko Cantelli Classes Shahar Mendelson Abstract We introduce a new parameter which
More informationOAK RIDGE NATIONAL LABORATORY
ORNL/TM-13339 OAK RDGE NATONAL LABORATORY 7+ A SMPLE ROTATONAL PENDULUM METHOD TO MEASURE THE RAD OF GYRATON OR MASS MOMENTS OF NERTA OF A ROTOR AND OTHER ASSEMBLES LOCKHEED M A R T N John B. Andriulli
More informationOn Learning µ-perceptron Networks with Binary Weights
On Learning µ-perceptron Networks with Binary Weights Mostefa Golea Ottawa-Carleton Institute for Physics University of Ottawa Ottawa, Ont., Canada K1N 6N5 050287@acadvm1.uottawa.ca Mario Marchand Ottawa-Carleton
More informationGA A25853 FAST ION REDISTRIBUTION AND IMPLICATIONS FOR THE HYBRID REGIME
GA A25853 FAST ION REDISTRIBUTION AND IMPLICATIONS FOR THE HYBRID REGIME by R. NAZIKIAN, M.E. AUSTIN, R.V. BUDNY, M.S. CHU, W.W. HEIDBRINK, M.A. MAKOWSKI, C.C. PETTY, P.A. POLITZER, W.M. SOLOMON, M.A.
More informationAustralian National University. Abstract. number of training examples necessary for satisfactory learning performance grows
The VC-Dimension and Pseudodimension of Two-Layer Neural Networks with Discrete Inputs Peter L. Bartlett Robert C. Williamson Department of Systems Engineering Research School of Information Sciences and
More informationAlamos National Laboratory is operated by the University of California for the United States Department of Energy under contract W-7405-ENG-36
LA- UR "6 Ea Alamos National Laboratory is operated by the University of California for the United States Department of Energy under contract W-7405-ENG-36 TITLE: AUTHOR(S): SUBMITTED TO: SPATIAL AND ANGULAR
More informationPAC Learning Using Nadaraya-Watson Estimator Based on Orthonormal Systems
PAC Learning Using Nadaraya-Watson Estimator Based on Orthonormal Systems Hongzhu Qiao Department of Mathematics and Physics Fort Valley State College Fort Valley, GA 31030 Nageswara S.V. Rao, V. Protopopescu
More informationNational Accelerator Laboratory
Fermi National Accelerator Laboratory FERMILAB-Conf-99/278-T The Heavy Hybrid Spectrum from NRQCD and the Born-Oppenheimer Approximation K.J. Juge, J. Kuti and C.J. Morningstar Fermi National Accelerator
More informationOn the Sample Complexity of Noise-Tolerant Learning
On the Sample Complexity of Noise-Tolerant Learning Javed A. Aslam Department of Computer Science Dartmouth College Hanover, NH 03755 Scott E. Decatur Laboratory for Computer Science Massachusetts Institute
More informationAC dipole based optics measurement and correction at RHIC
BNL-1132-213-CP AC dipole based optics measurement and correction at RHIC X. Shen, S. Y. Lee Indiana University of Bloomington, IN 4745, USA M. Bai, S. White, G. Robert-Demolaize, Y. Luo, A. Marusic BNL,
More informationPREDICTIVE MODELING OF PLASMA HALO EVOLUTION IN POST-THERMAL QUENCH DISRUPTING PLASMAS
GA A25488 PREDICTIVE MODELING OF PLASMA HALO EVOLUTION IN POST-THERMAL QUENCH DISRUPTING PLASMAS by D.A. HUMPHREYS, D.G. WHYTE, M. BAKHTIARI, R.D. DERANIAN, E.M. HOLLMANN, A.W. HYATT, T.C. JERNIGAN, A.G.
More informationPaper to be submitted to. Thermal Management Technology for Hydrogen Storage: Fullerene Option?
Paper to be submitted to eodf46 O&fhO DOE Hydrogen Program Review and Working Group Meetings April 29-May 3,1996 Miami, Florida Thermal Management Technology for Hydrogen Storage: Fullerene Option? J.
More informationAugust 3,1999. Stiffness and Strength Properties for Basic Sandwich Material Core Types UCRL-JC B. Kim, R.M. Christensen.
Preprint UCRL-JC-135347 Stiffness and Strength Properties for Basic Sandwich Material Core Types B. Kim, R.M. Christensen This article was submitted to ASME IMECE 99, Nashville, TN, November 14-19, 1999
More informationGA A23736 EFFECTS OF CROSS-SECTION SHAPE ON L MODE AND H MODE ENERGY TRANSPORT
GA A3736 EFFECTS OF CROSS-SECTION SHAPE ON L MODE AND H MODE ENERGY TRANSPORT by T.C. LUCE, C.C. PETTY, and J.E. KINSEY AUGUST DISCLAIMER This report was prepared as an account of work sponsored by an
More informationust/ aphysics Division, Argonne National Laboratory, Argonne, Illinois 60439, USA
The submitted manuscript has been created by the University of Chicago as Operator of Argonne N%tional Laboratory ( zargonne ) under ConIract No. W-31-109-ENG-38 with MJ4PR i@ -I OJ2 73 the U.S. Department
More informationCentrifugal Destabilization and Restabilization of Plane Shear Flows
Centrifugal Destabilization and Restabilization of Plane Shear Flows A. J. Conley Mathematics and Computer Science Division Argonne National Laboratory Argonne, L 60439 Abstract The flow of an incompressible
More information(4) How do you develop an optimal signal detection technique from the knowledge of
Signal and Noise in Global Warming Detection Final Report Gerald R. North, Principal Investigator Climate System Research Program, Texas A&M University, Texas 1. Program Objectives The specific objectives
More informationTell uric prof i 1 es across the Darrough Known Geothermal Resource Area, Nevada. Harold Kaufniann. Open-file Report No.
Tell uric prof i 1 es across the Darrough Known Geothermal Resource Area, Nevada c i 4 L BY D Harold Kaufniann U.S. Geological Survey. r,. Open-file Report No. 76-286 1976 \, *\. i \ -- i 1'.- - L -.,,-.,
More informationUniform Glivenko-Cantelli Theorems and Concentration of Measure in the Mathematical Modelling of Learning
Uniform Glivenko-Cantelli Theorems and Concentration of Measure in the Mathematical Modelling of Learning Martin Anthony Department of Mathematics London School of Economics Houghton Street London WC2A
More informationModified Kriging: Evaluation, Modification, Recommendations
UCRL-ID- 12873 1 Modified Kriging: Evaluation, Modification, Recommendations and C.A. Schultz S.C. Myers September 1997 This is an informal report intended primarily forinternal or limited external distribution.
More informationModeling Laser and e-beam Generated Plasma-Plume Experiments Using LASNEX
UCRL-ID-136726 Modeling Laser and e-beam Generated Plasma-Plume Experiments Using LASNEX D.D.-M. Ho December 1,1999 US. Department of Energy Approved for public release; further dissemination unlimited
More informationMaximal Width Learning of Binary Functions
Maximal Width Learning of Binary Functions Martin Anthony Department of Mathematics, London School of Economics, Houghton Street, London WC2A2AE, UK Joel Ratsaby Electrical and Electronics Engineering
More informationThe sample complexity of agnostic learning with deterministic labels
The sample complexity of agnostic learning with deterministic labels Shai Ben-David Cheriton School of Computer Science University of Waterloo Waterloo, ON, N2L 3G CANADA shai@uwaterloo.ca Ruth Urner College
More informationComments on the Geophysics paper Multiparameter 11norm. waveform fitting: Interpretation of Gulf of Mexico reflection
,..-., Comments on the Geophysics paper Multiparameter 11norm waveform fitting: Interpretation of Gulf of Mexico reflection seismograms by H. Djikp&s6 and A. Tarantola Susan E. Minkoff * t and William
More informationPAC Learning Algorithms for Functions Approximated by Feedforward Networkst
PAC Learning Algorithms for Functions Approximated by Feedforward Networkst Nageswara S. V. Rao Vladimir Prot opopescu Center for Engineering Systems Advanced Research Oak Ridge National Laboratory Oak
More informationFat-shattering. and the learnability of real-valued functions. Peter L. Bartlett. Department of Systems Engineering
Fat-shattering and the learnability of real-valued functions Peter L. Bartlett Department of Systems Engineering Research School of Information Sciences and Engineering Australian National University Canberra,
More informationGary E. Giles Computational Physics and Engineering Division. Jon S. Bullock Y-17npwlopment Division
ORNL/CP-95628 VALIDATION OF THE BEPLATE CODE b/jf? 7/()i%T-- Gary E. Giles Computational Physics and Engineering Division Jon S. Bullock Y-17npwlopment Division Oak Ridge National Laboratory' To be published
More informationLawrence Berkeley National Laboratory Lawrence Berkeley National Laboratory
Lawrence Berkeley National Laboratory Lawrence Berkeley National Laboratory Title ECLOUD in PS, PS+, SPS+: AN UPDATE Permalink https://escholarship.org/uc/item/7rf0rz Author Furman, M.A. Publication Date
More informationPlasma Response Control Using Advanced Feedback Techniques
Plasma Response Control Using Advanced Feedback Techniques by M. Clement 1 with J. M. Hanson 1, J. Bialek 1 and G. A. Navratil 1 1 Columbia University Presented at 59 th Annual APS Meeting Division of
More informationSimulation of Double-Null Divertor Plasmas with the UEDGE Code
Preprint UCRL-JC-134341 Simulation of Double-Null Divertor Plasmas with the UEDGE Code M. E. Rensink, S. L. Allen, G. 0. Porter, T. 0. Rognlien This article was submitted to 7th International Workshop
More informationGA A26057 DEMONSTRATION OF ITER OPERATIONAL SCENARIOS ON DIII-D
GA A26057 DEMONSTRATION OF ITER OPERATIONAL SCENARIOS ON DIII-D by E.J. DOYLE, J.C. DeBOO, T.A. CASPER, J.R. FERRON, R.J. GROEBNER, C.T. HOLCOMB, A.W. HYATT, G.L. JACKSON, R.J. LA HAYE, T.C. LUCE, G.R.
More informationEquivalencing the Collector System of a Large Wind Power Plant
Equivalencing the Collector System of a Large Wind Power Plant Presenter: Ed Muljadi National Wind Technology Center National Renewable Energy Laboratory Golden, Colorado USA IEEE Power Engineering Society
More informationUsing boxes and proximity to classify data into several categories
R u t c o r Research R e p o r t Using boxes and proximity to classify data into several categories Martin Anthony a Joel Ratsaby b RRR 7-01, February 01 RUTCOR Rutgers Center for Operations Research Rutgers
More informationScaling between K+ and proton production in nucleus-nucleus collisions *
Proc. Quark Matter 95 Monterey, CA January 9-, 9 9 5 I BNL-6 55 Scaling between K+ and proton production in nucleus-nucleus collisions * Ziping Chen and Chellis Chasman Dept. of Physics, Brookhaven National
More informationNational Accelerator Laboratory
Fermi National Accelerator Laboratory FERMILAB-Conf-99/292-E CDF and D0 New W Mass Results from CDF and D0 Bill Carithers Lawrence Berkeley Laboratory Berkeley, California Fermi National Accelerator Laboratory
More informationA Distributed Radiator, Heavy Ion Driven Inertial Confinement Fusion Target with Realistic, Multibeam Illumination Geometry
UCRL-JC-131974 PREPRINT A Distributed Radiator, Heavy Ion Driven Inertial Confinement Fusion Target with Realistic, Multibeam Illumination Geometry D. A. Callahan-Miller M. Tabak This paper was prepared
More informationUNIT OPERATIONS AND CHEMICAL PROCESSES. Alan M. Krichinsky
-DISCLAIMER This repon was prepared as an account of work won jo red tiv an agency o* the United States Government. Neither the United States Government nor any agency thereof, nor any of their emsloyees,
More informationDevelopment of a High Intensity EBIT for Basic and Applied Science
UCRL-ID- 129832 Development of a High Intensity EBIT for Basic and Applied Science R.E. Marrs D. Schneider February 5,1998 This is an informal report intended primarily for internal or limited external
More informationThe Performance of a New Hybrid Classifier Based on Boxes and Nearest Neighbors
The Performance of a New Hybrid Classifier Based on Boxes and Nearest Neighbors Martin Anthony Department of Mathematics London School of Economics and Political Science Houghton Street, London WC2A2AE
More informationNeural Network Learning: Testing Bounds on Sample Complexity
Neural Network Learning: Testing Bounds on Sample Complexity Joaquim Marques de Sá, Fernando Sereno 2, Luís Alexandre 3 INEB Instituto de Engenharia Biomédica Faculdade de Engenharia da Universidade do
More informationMACHINE LEARNING. Vapnik-Chervonenkis (VC) Dimension. Alessandro Moschitti
MACHINE LEARNING Vapnik-Chervonenkis (VC) Dimension Alessandro Moschitti Department of Information Engineering and Computer Science University of Trento Email: moschitti@disi.unitn.it Computational Learning
More information0STI. E. Hammerberg, XNH MD SIMULATIONS OF DUSTY PLASMA CRYSTAL FORMATION: PRELIMINARY RESULTS M. J. S. Murillo, XPA
LA-UR- - 9 7 4 16 3 A proved for public release; dpstnbution is unlimited. Title: Author(s): Submitted to MD SIMULATIONS OF DUSTY PLASMA CRYSTAL FORMATION: PRELIMINARY RESULTS M. J. B. G. W. D. S. Murillo,
More informationIMPACT OF EDGE CURRENT DENSITY AND PRESSURE GRADIENT ON THE STABILITY OF DIII-D HIGH PERFORMANCE DISCHARGES
IMPACT OF EDGE CURRENT DENSITY AND PRESSURE GRADIENT ON THE STABILITY OF DIII-D HIGH PERFORMANCE DISCHARGES by L.L. LAO, J.R. FERRON, E.J. STRAIT, V.S. CHAN, M.S. CHU, E.A. LAZARUS, TIC. LUCE, R.L. MILLER,
More informationRay M. Stringfield Robert J. Kares J. R. Thomas, Jr.
U4JR-96-1107 * v TITLE: AU THOR(S): SUBMITTED TO: TEMPERATURE DISTRIBUTION IN A FLOWING FLUID HEATED IN A MICROWAVE RESONANT CAVI'W Eric M. Nelson Ray M. Stringfield Robert J. Kares J. R. Thomas, Jr. AOT-9
More informationUNDERSTANDING TRANSPORT THROUGH DIMENSIONLESS PARAMETER SCALING EXPERIMENTS
UNDERSTANDING TRANSPORT THROUGH DIMENSIONLESS PARAMETER SCALING EXPERIMENTS by C.C. PETTY and T.C. LUCE JULY 1997 CENERaL ATOMRCS This report was prepared as an account of work sponsored by an agency of
More informationAbstract of paper proposed for the American Nuclear Society 1997 Winter Meeting Albuquerque, New Mexico November 16-20, 1997
P i Abstract of paper proposed for the American Nuclear Society 1997 Winter Meeting Albuquerque, New Mexico November 16-20, 1997 JUL 2 1 1997 OSTI Converting wmo Production from High- to Low-EnrichedUranium
More informationAnalysis of Shane Telescope Aberration and After Collimation
UCRL-ID- 133548 Analysis of Shane Telescope Aberration and After Collimation Before Don Gavel January 26,1999 This is an informal report intended primarily for internal or limited external distribution.
More informationA Few-Group Delayed Neutron Model Based on a Consistent Set of Decay Constants. Joann M. Campbell Gregory D. Spriggs
Title: Author(s): Submitted to: A Few-Group Delayed Neutron Model Based on a Consistent Set of Decay Constants Joann M. Campbell Gregory D. Spriggs American Nuclear S o c A y 1998 Summer Meeting June 7-11,1998
More informationTOWARDS EVEN AND ODD SQUEEZED NUMBER STATES NIETO, MICHAEL M
Approved for public release; distribution is unlimited. Title TOARDS EVEN AND ODD SQUEEZED NUMBER STATES L Author(s NIETO, MICHAEL M 0 + pc13 pc13 0 Submitted t CONFERENCE PROCEEDINGS "FIFTH INTERNATIONAL
More informationThe Radiological Hazard of Plutonium Isotopes and Specific Plutonium Mixtures
LA-13011 The Radiological Hazard of Plutonium Isotopes and Specific Plutonium Mixtures Los Alamos NATIONAL LABORATORY Los Alamos National Laboratory is operated by the University of California for the
More informationIMAGING OF HETEROGENEOUS MATERIALS BY. P. Staples, T. H. Prettyman, and J. Lestone
Tifle: IMAGING OF HETEROGENEOUS MATERIALS BY PROMPT GAMMA-RAY NEUTRON ACTIVATION ANALYSIS R'6iCElVED OCT 0 5 998 Author@): P. Staples, T. H. Prettyman, and J. Lestone os Submitted to: 998 Symposium on
More informationPrinciples of Risk Minimization for Learning Theory
Principles of Risk Minimization for Learning Theory V. Vapnik AT &T Bell Laboratories Holmdel, NJ 07733, USA Abstract Learning is posed as a problem of function estimation, for which two principles of
More informationRECXWH2 W/o s3-1
.,, Nuclear Energy Research Initiative (NERI) DE-FG03-99SF21922 Program Tasks 1 & 3 Quarterly Technical Progress Report July 1- September 30, 2000 An Innovative Reactor Analysis Methodology Based on a
More information~ _- IDOCLRXKT DMSP SATELLITE DETECTIONS OF GAMMA-RAY BURSTS. J. Terrell, NIS-2 P. Lee, NIS-2 R W.
TITLE: AUTHOR(S): SUBMITTED TO: DMSP SATELLITE DETECTIONS OF GAMMARAY BURSTS J. Terrell, NIS2 P. Lee, NIS2 R W. Klebesadel, NIS2 Huntsville GRB Symposium Proceddings, Huntsville, AL NATIONAL LABORATORY
More informationOn A-distance and Relative A-distance
1 ADAPTIVE COMMUNICATIONS AND SIGNAL PROCESSING LABORATORY CORNELL UNIVERSITY, ITHACA, NY 14853 On A-distance and Relative A-distance Ting He and Lang Tong Technical Report No. ACSP-TR-08-04-0 August 004
More informationLos Alamos IMPROVED INTRA-SPECIES COLLISION MODELS FOR PIC SIMULATIONS. Michael E. Jones, XPA Don S. Lemons, XPA & Bethel College Dan Winske, XPA
, LA- U R-= Approved for public release; distribution is unlimited. m Title: Author(s) Submitted tc IMPROED INTRA-SPECIES COLLISION MODELS FOR PIC SIMULATIONS Michael E. Jones, XPA Don S. Lemons, XPA &
More informationCurvature of a Cantilever Beam Subjected to an Equi-Biaxial Bending Moment. P. Krulevitch G. C. Johnson
UCRL-JC-30440 PREPRINT Curvature of a Cantilever Beam Subjected to an Equi-Biaxial Bending Moment P. Krulevitch G. C. Johnson This paper was prepared for submittal to the Materials Research Society Spring
More informationApplications of Pulse Shape Analysis to HPGe Gamma-Ray Detectors
UCRL-JC- 134555 PREPRINT Applications of Pulse Shape Analysis to HPGe Gamma-Ray Detectors GJ. Schmid D.A. Beckedahl JJ. Blair J.E. Kammeraad This paper was prepared for submittal to the American Nuclear
More informationLinear Dependency Between and the Input Noise in -Support Vector Regression
544 IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 14, NO. 3, MAY 2003 Linear Dependency Between the Input Noise in -Support Vector Regression James T. Kwok Ivor W. Tsang Abstract In using the -support vector
More informationYale University Department of Computer Science. The VC Dimension of k-fold Union
Yale University Department of Computer Science The VC Dimension of k-fold Union David Eisenstat Dana Angluin YALEU/DCS/TR-1360 June 2006, revised October 2006 The VC Dimension of k-fold Union David Eisenstat
More informationTurbulent Scaling in Fluids. Robert Ecke, MST-10 Ning Li, MST-10 Shi-Yi Li, T-13 Yuanming Liu, MST-10
Title: Author(s): Submitted to: Turbulent Scaling in Fluids Robert Ecke, MST-10 Ning Li, MST-10 Shi-Yi Li, T-13 Yuanming Liu, MST-10 RECEIVED OCT 3 I 1998 DOE Office of Scientific and Technical Information
More informationBWXT Y-12 Y-12. A BWXT/Bechtel Enterprise SMALL, PORTABLE, LIGHTWEIGHT DT NEUTRON GENERATOR FOR USE WITH NMIS
BWXT Y-12 A BWXT/Bechtel Enterprise Report No.: Y/LB-16,078 (Paper) SMALL, PORTABLE, LIGHTWEIGHT DT NEUTRON GENERATOR FOR USE WITH NMIS J. Reichardt J. T. Mihalczo R. B. Oberer L. G. Chiang J. K. Mattingly
More information41--tsh.. J. Halperin M. P. Lietzke ORNL-2823 EFFECTIVE CADMIUM CUTOFF ENERGIES SUPPLEMENT OAK RIDGE NATIONAL LABORATORY. R. W.
41--tsh.. ORNL-2823 '-~]\ Suppleent 'T UC-4-Cheistry-General EFFECTIVE CADMIUM CUTOFF ENERGIES SUPPLEMENT R. W. Stoughton J. Halperin M. P. Lietzke OAK RIDGE NATIONAL LABORATORY operated by UNION CARBIDE
More informationContractor Name and Address: Oxy USA, Inc. (Oxy), Midland, Texas OBJECTIVES
1 F TITLE: APPLICATION OF RESERVOIR CHARACTERIZATION AND ADVANCED TECHNOLOGY TO IMPROVE RECOVERY AND ECONOMICS IN A LOWER QUALITY SHALLOW SHELF CARBONATE RESERVOIR Cooperative Agreement No.: DE - FC22-948C14990
More informationMACHINE LEARNING - CS671 - Part 2a The Vapnik-Chervonenkis Dimension
MACHINE LEARNING - CS671 - Part 2a The Vapnik-Chervonenkis Dimension Prof. Dan A. Simovici UMB Prof. Dan A. Simovici (UMB) MACHINE LEARNING - CS671 - Part 2a The Vapnik-Chervonenkis Dimension 1 / 30 The
More informationGA A22689 SLOW LINER FUSION
GA A22689 SLOW LINER FUSION by AUGUST 1997 DISCLAIMER This report was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor any
More informationGA A27805 EXPANDING THE PHYSICS BASIS OF THE BASELINE Q=10 SCENRAIO TOWARD ITER CONDITIONS
GA A27805 EXPANDING THE PHYSICS BASIS OF THE BASELINE Q=10 SCENRAIO TOWARD ITER CONDITIONS by T.C. LUCE, G.L. JACKSON, T.W. PETRIE, R.I. PINSKER, W.M. SOLOMON, F. TURCO, N. COMMAUX, J.R. FERRON, A.M. GAROFALO,
More informationUse of AVHRR-Derived Spectral Reflectances to Estimate Surface Albedo across the Southern Great Plains Cloud and Radiation Testbed (CART) Site
i Use of AVHRR-Derived Spectral Reflectances to Estimate Surface Albedo across the Southern Great Plains Cloud and Radiation Testbed (CART) Site J. Qiu and W. Gao Environmental Research Division Argonne
More informationRWM FEEDBACK STABILIZATION IN DIII D: EXPERIMENT-THEORY COMPARISONS AND IMPLICATIONS FOR ITER
GA A24759 RWM FEEDBACK STABILIZATION IN DIII D: EXPERIMENT-THEORY COMPARISONS AND IMPLICATIONS FOR ITER by A.M. GAROFALO, J. BIALEK, M.S. CHANCE, M.S. CHU, D.H. EDGELL, G.L. JACKSON, T.H. JENSEN, R.J.
More informationQuarterly Report April 1 - June 30, By: Shirley P. Dutton. Work Performed Under Contract No.: DE-FC22-95BC14936
DE-FC22-95BC14936--18 Application of Advanced Reservoir Characterization, Simulation, and Production Optimization Strategies to Maximize Recovery in Slope, and Basin Clastic Reservoirs, West Texas (Delaware
More information8STATISTICAL ANALYSIS OF HIGH EXPLOSIVE DETONATION DATA. Beckman, Fernandez, Ramsay, and Wendelberger DRAFT 5/10/98 1.
8STATISTICAL ANALYSIS OF HIGH EXPLOSIVE DETONATION DATA Beckman, Fernandez, Ramsay, and Wendelberger DRAFT 5/1/98 1. INTRODUCTION Statistical analysis of data for two different high explosives was performed.
More informationABSTRACT INTRODUCTION
, w 1 Real-Time Mass Spectrometry of ndividual irborne Bacteria William B. Whitten, Rainer. Gieray, Peter T.. Reilly, Mo Yang, and J. Michael Ramsey Oak Ridge National Laboratory ; 3.yyz g-?. Oak Ridge,
More informationGA A27857 IMPACT OF PLASMA RESPONSE ON RMP ELM SUPPRESSION IN DIII-D
GA A27857 IMPACT OF PLASMA RESPONSE ON RMP ELM SUPPRESSION IN DIII-D by A. WINGEN, N.M. FERRARO, M.W. SHAFER, E.A. UNTERBERG, T.E. EVANS, D.L. HILLIS, and P.B. SNYDER JULY 2014 DISCLAIMER This report was
More informationGA A27235 EULERIAN SIMULATIONS OF NEOCLASSICAL FLOWS AND TRANSPORT IN THE TOKAMAK PLASMA EDGE AND OUTER CORE
GA A27235 EULERIAN SIMULATIONS OF NEOCLASSICAL FLOWS AND TRANSPORT IN THE TOKAMAK PLASMA EDGE AND OUTER CORE by E.A. BELLI, J.A. BOEDO, J. CANDY, R.H. COHEN, P. COLELLA, M.A. DORF, M.R. DORR, J.A. HITTINGER,
More informationOptimal global rates of convergence for interpolation problems with random design
Optimal global rates of convergence for interpolation problems with random design Michael Kohler 1 and Adam Krzyżak 2, 1 Fachbereich Mathematik, Technische Universität Darmstadt, Schlossgartenstr. 7, 64289
More informationAPPLICATION SINGLE ION ACTIVITY COEFFICIENTS TO DETERMINE SOLVENT EXTRACTION MECHANISM FOR COMPONENTS OF NUCLEAR WASTE
APPLCATON SNGLE ON ACTVTY COEFFCENTS TO DETERMNE SOLVENT EXTRACTON MECHANSM FOR COMPONENTS OF HGH LEVEL NUCLEAR WASTE by L. Nufiez and G. F. Vandegrift The submitted manuscript has been authored by a contractor
More informationUnderstanding Generalization Error: Bounds and Decompositions
CIS 520: Machine Learning Spring 2018: Lecture 11 Understanding Generalization Error: Bounds and Decompositions Lecturer: Shivani Agarwal Disclaimer: These notes are designed to be a supplement to the
More information